{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:R4ONF3OHSP5U7S4MYZG6HCW3KC","short_pith_number":"pith:R4ONF3OH","canonical_record":{"source":{"id":"2409.03444","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T11:49:53Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"title_canon_sha256":"6bb3ee3557965ddb1791e5d7ab8a927373568578d81d40d2bfcdeb66ad901636","abstract_canon_sha256":"9a45ef64857911713d3ce08cbc7d29677a870154eedfd7b8211118f27813f6f0"},"schema_version":"1.0"},"canonical_sha256":"8f1cd2edc793fb4fcb8cc64de38adb50a0e5e3f0f4e92e769f540ab146b864fb","source":{"kind":"arxiv","id":"2409.03444","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03444","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03444v1","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03444","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"R4ONF3OHSP5U","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"R4ONF3OHSP5U7S4M","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"R4ONF3OH","created_at":"2026-07-05T09:03:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:R4ONF3OHSP5U7S4MYZG6HCW3KC","target":"record","payload":{"canonical_record":{"source":{"id":"2409.03444","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T11:49:53Z","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"title_canon_sha256":"6bb3ee3557965ddb1791e5d7ab8a927373568578d81d40d2bfcdeb66ad901636","abstract_canon_sha256":"9a45ef64857911713d3ce08cbc7d29677a870154eedfd7b8211118f27813f6f0"},"schema_version":"1.0"},"canonical_sha256":"8f1cd2edc793fb4fcb8cc64de38adb50a0e5e3f0f4e92e769f540ab146b864fb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:31.458200Z","signature_b64":"S3abmR95LZ0Zwx0Eje8KEkjQRH8DA2c/1GjTFUCNZ8j03bJ/80RwdvtSCzrZTSWMqF/yttnsGoM4msjSllRYDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1cd2edc793fb4fcb8cc64de38adb50a0e5e3f0f4e92e769f540ab146b864fb","last_reissued_at":"2026-07-05T09:03:31.457606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:31.457606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.03444","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yFQbLmC89mVVswp8l3bx+7IA3V6ZeS/OxTG8MloJvbzjZWB6vH6qxcfc95K+B8yEgJ4gQ4Haln0rVkzosuVcCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:26:10.177486Z"},"content_sha256":"f39d4e9f9e2ecd639d70e132447b039153f4ad41834c21a0aa90c4451eea2b4a","schema_version":"1.0","event_id":"sha256:f39d4e9f9e2ecd639d70e132447b039153f4ad41834c21a0aa90c4451eea2b4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:R4ONF3OHSP5U7S4MYZG6HCW3KC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"primary_cat":"cs.CL","authors_text":"Markus J. Buehler, Rachel K. Luu, Wei Lu","submitted_at":"2024-09-05T11:49:53Z","abstract_excerpt":"The advancement of Large Language Models (LLMs) for domain applications in fields such as materials science and engineering depends on the development of fine-tuning strategies that adapt models for specialized, technical capabilities. In this work, we explore the effects of Continued Pretraining (CPT), Supervised Fine-Tuning (SFT), and various preference-based optimization approaches, including Direct Preference Optimization (DPO) and Odds Ratio Preference Optimization (ORPO), on fine-tuned LLM performance. Our analysis shows how these strategies influence model outcomes and reveals that the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03444","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2409.03444/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZoWk6WSMnwXrMS2FP6Q2GqTa86rVSvC480NfhD0FIG0VBwYxtTuBJnlVfXcc3g2eNM/W9HMHZ94rof7WsIZUBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:26:10.178042Z"},"content_sha256":"9eb3e9ad8b656dcc1908846895bbfba8d3eb8ce8da4b6ba30a5bbe00eb3844d1","schema_version":"1.0","event_id":"sha256:9eb3e9ad8b656dcc1908846895bbfba8d3eb8ce8da4b6ba30a5bbe00eb3844d1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4ONF3OHSP5U7S4MYZG6HCW3KC/bundle.json","state_url":"https://pith.science/pith/R4ONF3OHSP5U7S4MYZG6HCW3KC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4ONF3OHSP5U7S4MYZG6HCW3KC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T22:26:10Z","links":{"resolver":"https://pith.science/pith/R4ONF3OHSP5U7S4MYZG6HCW3KC","bundle":"https://pith.science/pith/R4ONF3OHSP5U7S4MYZG6HCW3KC/bundle.json","state":"https://pith.science/pith/R4ONF3OHSP5U7S4MYZG6HCW3KC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4ONF3OHSP5U7S4MYZG6HCW3KC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:R4ONF3OHSP5U7S4MYZG6HCW3KC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"9a45ef64857911713d3ce08cbc7d29677a870154eedfd7b8211118f27813f6f0","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T11:49:53Z","title_canon_sha256":"6bb3ee3557965ddb1791e5d7ab8a927373568578d81d40d2bfcdeb66ad901636"},"schema_version":"1.0","source":{"id":"2409.03444","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03444","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03444v1","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03444","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"pith_short_12","alias_value":"R4ONF3OHSP5U","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"pith_short_16","alias_value":"R4ONF3OHSP5U7S4M","created_at":"2026-07-05T09:03:31Z"},{"alias_kind":"pith_short_8","alias_value":"R4ONF3OH","created_at":"2026-07-05T09:03:31Z"}],"graph_snapshots":[{"event_id":"sha256:9eb3e9ad8b656dcc1908846895bbfba8d3eb8ce8da4b6ba30a5bbe00eb3844d1","target":"graph","created_at":"2026-07-05T09:03:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.03444/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The advancement of Large Language Models (LLMs) for domain applications in fields such as materials science and engineering depends on the development of fine-tuning strategies that adapt models for specialized, technical capabilities. In this work, we explore the effects of Continued Pretraining (CPT), Supervised Fine-Tuning (SFT), and various preference-based optimization approaches, including Direct Preference Optimization (DPO) and Odds Ratio Preference Optimization (ORPO), on fine-tuned LLM performance. Our analysis shows how these strategies influence model outcomes and reveals that the ","authors_text":"Markus J. Buehler, Rachel K. Luu, Wei Lu","cross_cats":["cond-mat.mtrl-sci","cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T11:49:53Z","title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03444","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f39d4e9f9e2ecd639d70e132447b039153f4ad41834c21a0aa90c4451eea2b4a","target":"record","created_at":"2026-07-05T09:03:31Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"9a45ef64857911713d3ce08cbc7d29677a870154eedfd7b8211118f27813f6f0","cross_cats_sorted":["cond-mat.mtrl-sci","cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T11:49:53Z","title_canon_sha256":"6bb3ee3557965ddb1791e5d7ab8a927373568578d81d40d2bfcdeb66ad901636"},"schema_version":"1.0","source":{"id":"2409.03444","kind":"arxiv","version":1}},"canonical_sha256":"8f1cd2edc793fb4fcb8cc64de38adb50a0e5e3f0f4e92e769f540ab146b864fb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f1cd2edc793fb4fcb8cc64de38adb50a0e5e3f0f4e92e769f540ab146b864fb","first_computed_at":"2026-07-05T09:03:31.457606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:31.457606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S3abmR95LZ0Zwx0Eje8KEkjQRH8DA2c/1GjTFUCNZ8j03bJ/80RwdvtSCzrZTSWMqF/yttnsGoM4msjSllRYDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:31.458200Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03444","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f39d4e9f9e2ecd639d70e132447b039153f4ad41834c21a0aa90c4451eea2b4a","sha256:9eb3e9ad8b656dcc1908846895bbfba8d3eb8ce8da4b6ba30a5bbe00eb3844d1"],"state_sha256":"774601ca3f88e490369b10faa4e13514f91a4d768ba8311a93d45d08b406b9a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UTBAXSpNx5NRM9ZpANLtWLpLMOBADLrWXtoQ7mrUE08IL7+OVJbVwFvgoj+3VfkV9QpY8zh6M7vxQgWT6AEBAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:26:10.182640Z","bundle_sha256":"7d529fc09eeddd86f4e1a4100be8f9f041077de6f48889014a40c59b23dd3bf4"}}